Use this as the primary tool to list the log sinks in a Google Cloud project. Log sinks control how Cloud Logging routes your logs to supported destinations, such as Cloud Storage buckets, BigQuery datasets, or Pub/Sub topics. This is useful for understanding your logging export configurations.
AI agents call list_sinks to retrieve information from Storage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates log sink configurations without modifying, deleting, or executing operations. It is a query/discovery function that poses minimal risk—it only exposes information about existing logging routes. An AI agent misusing this tool would have limited impact, as it cannot change logging behavior or access log data itself, only metadata about sink configurations.
From the tool's definition Tool name is 'list_sinks' and description states it 'list[s] the log sinks in a Google Cloud project' and is 'useful for understanding your logging export configurations.' The verb 'list' and action of querying/retrieving existing sink configurations with no…
Attacks that exploit this kind of access
Use this as the primary tool to list the log sinks in a Google Cloud project. Log sinks control how Cloud Logging routes your logs to supported destinations, such as Cloud Storage buckets, BigQuery datasets, or Pub/Sub topics. This is useful for understanding your logging export configurations. It is categorised as a Read tool in the Storage MCP Server, which means it retrieves data without modifying state.
Register the Storage MCP server in PolicyLayer and add a rule for list_sinks: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Storage. Nothing to install.
list_sinks is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_sinks rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_sinks. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_sinks is provided by the Storage MCP server (@google-cloud/storage-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.